论文标题
使用贝叶斯神经网络同时进行不确定性定量的粒子图像速度计分析
Particle image velocimetry analysis with simultaneous uncertainty quantification using Bayesian neural networks
论文作者
论文摘要
粒子图像速度法（PIV）是从图像中提取流场的实验流体力学中的有效工具。最近，卷积神经网络（CNN）已被用于与经典方法相同的准确性进行PIV分析。在这里，我们扩展了CNN的使用来分析PIV数据，同时在推断的流场上提供同时的不确定性量化。我们在本文中采用的方法是贝叶斯卷积神经网络（BCNN），该卷积神经网络（BCNN）通过各种贝叶斯学习了CNN权重的分布。我们比较了三种不同BCNN模型的性能。第一个网络仅从图像询问区域估算流速度。我们的第二个模型学会从图像询问区域和询问区域互相关图中推断出速度。最后，我们最佳性能网络仅从询问区域互相关图中得出速度。我们发现，使用询问区域互相关图作为输入的BCNN比仅使用审问窗口作为输入的互换映射更好，并讨论了可能是这种情况的原因。此外，我们在完整的测试图像对上测试了最佳性能BCNN，这表明可以在其95％的置信区间内捕获100％的真粒子位移。最后，我们表明可以将BCNN概括为与多通PIV算法一起使用，准确性中等损失，这可以通过未来的鉴定和培训方案来克服。据我们所知，这是使用贝叶斯神经网络执行粒子图像速度法的首次努力。
Particle image velocimetry (PIV) is an effective tool in experimental fluid mechanics to extract flow fields from images. Recently, convolutional neural networks (CNNs) have been used to perform PIV analysis with accuracy on par with classical methods. Here we extend the use of CNNs to analyze PIV data while providing simultaneous uncertainty quantification on the inferred flow field. The method we apply in this paper is a Bayesian convolutional neural network (BCNN) which learns distributions of the CNN weights through variational Bayes. We compare the performance of three different BCNN models. The first network estimates flow velocity from image interrogation regions only. Our second model learns to infer velocity from both the image interrogation regions and interrogation region cross-correlation maps. Finally, our best performing network derives velocities from interrogation region cross-correlation maps only. We find that BCNNs using interrogation region cross-correlation maps as inputs perform better than those using interrogation windows only as inputs and discuss reasons why this may be the case. Additionally, we test the best performing BCNN on a full test image pair, showing that 100% of true particle displacements can be captured within its 95% confidence interval. Finally, we show that BCNNs can be generalized to be used with multi-pass PIV algorithms with a moderate loss in accuracy, which may be overcome by future work on finetuning and training schemes. To our knowledge, this is the first effort to use Bayesian neural networks to perform particle image velocimetry.
